sastt-case2.sys.rttm.filt.mdeval 4.97 KB
command line (run on 2009 May 1 at 15:00:28) Version: 22  ../../md-eval/md-eval.pl -nafcs -c 0.25 -o -r sastt-case2.ref.rttm.filt -s sastt-case2.sys.rttm.filt -M sastt-case2.sys.rttm.filt.mdeval.spkrmap

Time-based metadata alignment

Metadata evaluation parameters:
    time-optimized metadata mapping
        max gap between matching metadata events = 1 sec
        max extent to match for SU's = 0.5 sec

Speaker Diarization evaluation parameters:
    The max time to extend no-score zones for NON-LEX exclusions is 0.5 sec
    The no-score collar at SPEAKER boundaries is 0.25 sec

Exclusion zones for evaluation and scoring are:
                             -----MetaData-----        -----SpkrData-----
     exclusion set name:     DEFAULT    DEFAULT        DEFAULT    DEFAULT
     token type/subtype      no-eval   no-score        no-eval   no-score
             (UEM)              X                         X
         LEXEME/un-lex                    X                          
        NON-LEX/breath                                              X
        NON-LEX/cough                                               X
        NON-LEX/laugh                                               X
        NON-LEX/lipsmack                                            X
        NON-LEX/other                                               X
        NON-LEX/sneeze                                              X
        NOSCORE/<na>            X         X               X         X
 NO_RT_METADATA/<na>            X                                    
             SU/unannotated               X                          

*** Performance analysis for Speaker Diarization for c=1 f=VT_20051027-1400 ***

    EVAL TIME =      4.88 secs
  EVAL SPEECH =      4.88 secs (100.0 percent of evaluated time)
  SCORED TIME =      1.24 secs ( 25.3 percent of evaluated time)
SCORED SPEECH =      1.24 secs (100.0 percent of scored time)
   EVAL WORDS =     34        
 SCORED WORDS =     10         ( 29.4 percent of evaluated words)
---------------------------------------------
MISSED SPEECH =      0.00 secs (  0.0 percent of scored time)
FALARM SPEECH =      0.00 secs (  0.0 percent of scored time)
 MISSED WORDS =      0         (  0.0 percent of scored words)
---------------------------------------------
SCORED SPEAKER TIME =      2.37 secs (191.8 percent of scored speech)
MISSED SPEAKER TIME =      1.13 secs ( 47.4 percent of scored speaker time)
FALARM SPEAKER TIME =      0.00 secs (  0.0 percent of scored speaker time)
 SPEAKER ERROR TIME =      0.00 secs (  0.0 percent of scored speaker time)
SPEAKER ERROR WORDS =     10         (100.0 percent of scored speaker words)
---------------------------------------------
 OVERALL SPEAKER DIARIZATION ERROR = 47.43 percent of scored speaker time  `(c=1 f=VT_20051027-1400)
---------------------------------------------
 Speaker type confusion matrix -- speaker weighted
  REF\SYS (count)      unknown               MISS              
unknown                   2 /  50.0%          2 /  50.0%
  FALSE ALARM             0 /   0.0%
---------------------------------------------
 Speaker type confusion matrix -- time weighted
  REF\SYS (seconds)    unknown               MISS              
unknown                1.25 /  52.6%       1.13 /  47.4%
  FALSE ALARM          0.00 /   0.0%
---------------------------------------------

*** Performance analysis for Speaker Diarization for ALL ***

    EVAL TIME =      4.88 secs
  EVAL SPEECH =      4.88 secs (100.0 percent of evaluated time)
  SCORED TIME =      1.24 secs ( 25.3 percent of evaluated time)
SCORED SPEECH =      1.24 secs (100.0 percent of scored time)
   EVAL WORDS =     34        
 SCORED WORDS =     10         ( 29.4 percent of evaluated words)
---------------------------------------------
MISSED SPEECH =      0.00 secs (  0.0 percent of scored time)
FALARM SPEECH =      0.00 secs (  0.0 percent of scored time)
 MISSED WORDS =      0         (  0.0 percent of scored words)
---------------------------------------------
SCORED SPEAKER TIME =      2.37 secs (191.8 percent of scored speech)
MISSED SPEAKER TIME =      1.13 secs ( 47.4 percent of scored speaker time)
FALARM SPEAKER TIME =      0.00 secs (  0.0 percent of scored speaker time)
 SPEAKER ERROR TIME =      0.00 secs (  0.0 percent of scored speaker time)
SPEAKER ERROR WORDS =     10         (100.0 percent of scored speaker words)
---------------------------------------------
 OVERALL SPEAKER DIARIZATION ERROR = 47.43 percent of scored speaker time  `(ALL)
---------------------------------------------
 Speaker type confusion matrix -- speaker weighted
  REF\SYS (count)      unknown               MISS              
unknown                   2 /  50.0%          2 /  50.0%
  FALSE ALARM             0 /   0.0%
---------------------------------------------
 Speaker type confusion matrix -- time weighted
  REF\SYS (seconds)    unknown               MISS              
unknown                1.25 /  52.6%       1.13 /  47.4%
  FALSE ALARM          0.00 /   0.0%
---------------------------------------------